In this paper we have addressed the problem of adopting in a combined way a genetic algorithm and the Hough transform for implementing an auto tracking method in a video conference system. By applying this method we have been able to track an object that moves slowly following quite parallel trajectories. The proposed algorithm considers just the shape of the object to be tracked and a priori known as a template, without taking into account other several characteristics of images like colour or texture. Because the implementation of Hough transform is a problem of maximising a function with particular constraints, and each run of evaluating Hough transform is time consuming, in this paper we have adopted a particular genetic algorithm to evaluate the rectangular region in which evaluate the Hough transform. The genetic algorithm used elitistic strategy, fitness sharing, mating restriction, adaptive rate of mutation and adaptive rate of cross-over with a double cross point. Moreover, in this paper, since the evaluation of Hough transform is very time consuming, we have addressed the strategy of dividing the whole scene in different shorter window in order to partition the evaluating load on parallel DSP.

Video Saurus System: movement evaluation by a genetic algorithm

MASTRONARDI, Giuseppe;BEVILACQUA, Vitoantonio
2003

Abstract

In this paper we have addressed the problem of adopting in a combined way a genetic algorithm and the Hough transform for implementing an auto tracking method in a video conference system. By applying this method we have been able to track an object that moves slowly following quite parallel trajectories. The proposed algorithm considers just the shape of the object to be tracked and a priori known as a template, without taking into account other several characteristics of images like colour or texture. Because the implementation of Hough transform is a problem of maximising a function with particular constraints, and each run of evaluating Hough transform is time consuming, in this paper we have adopted a particular genetic algorithm to evaluate the rectangular region in which evaluate the Hough transform. The genetic algorithm used elitistic strategy, fitness sharing, mating restriction, adaptive rate of mutation and adaptive rate of cross-over with a double cross point. Moreover, in this paper, since the evaluation of Hough transform is very time consuming, we have addressed the strategy of dividing the whole scene in different shorter window in order to partition the evaluating load on parallel DSP.
Computational Intelligence for Measurement Systems and Applications, CIMSA '03.
0-7803-7783-4
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11589/14019
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 0
social impact